Showing eess.SYShow all
2 papers · 1 filter
eess.SY2026
Stable Multi-Step Rollouts via Uncertainty-Guided Hybrid Dynamics
Andrei Maalberg, Axel Neumann, Jens Knobloch
Multi-step rollouts are essential for model-based reinforcement learning (RL) and predictive control, yet learned dynamics models often become unstable when recursively applied, le…
eess.SY2026
KIND: A Kalman-Inspired Adaptive Estimator for SRF Cavity Detuning
Andrei Maalberg, Axel Neumann, Pablo Echevarria +2
Superconducting radio frequency cavities with a high quality factor enable energy-efficient accelerator operation but are very sensitive to mechanical disturbances that detune thei…